metadata
base_model: vinai/phobert-base-v2
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: PhoBERT-aug_replace_synonym-aug_insert_w2v
results: []
PhoBERT-aug_replace_synonym-aug_insert_w2v
This model is a fine-tuned version of vinai/phobert-base-v2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.3269
- Accuracy: 0.68
- F1: 0.6858
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.895 | 1.0 | 85 | 0.7598 | 0.65 | 0.5672 |
| 0.5508 | 2.0 | 170 | 0.7204 | 0.69 | 0.6897 |
| 0.3688 | 3.0 | 255 | 0.8039 | 0.72 | 0.7133 |
| 0.2403 | 4.0 | 340 | 0.9418 | 0.66 | 0.6672 |
| 0.1453 | 5.0 | 425 | 1.1062 | 0.67 | 0.6755 |
| 0.1089 | 6.0 | 510 | 1.2567 | 0.68 | 0.6834 |
| 0.0843 | 7.0 | 595 | 1.3071 | 0.67 | 0.6755 |
| 0.0779 | 8.0 | 680 | 1.3269 | 0.68 | 0.6858 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3